{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:72NTKJFBOB7X6UPFXKYY4JGD3A","short_pith_number":"pith:72NTKJFB","canonical_record":{"source":{"id":"2311.01052","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-02T07:54:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c0196bd91b80f82f8038f1df0294ff333fef1884615cbb71388a8e3e9564bcb4","abstract_canon_sha256":"19a7eadf348ee7122067236a2f80efbdc8d6b2b38c7824d0632f5bc9a1b2ba30"},"schema_version":"1.0"},"canonical_sha256":"fe9b3524a1707f7f51e5bab18e24c3d83ca002de570917f673916bd32e75a783","source":{"kind":"arxiv","id":"2311.01052","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01052","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01052v2","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01052","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"pith_short_12","alias_value":"72NTKJFBOB7X","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"pith_short_16","alias_value":"72NTKJFBOB7X6UPF","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"pith_short_8","alias_value":"72NTKJFB","created_at":"2026-07-05T07:13:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:72NTKJFBOB7X6UPFXKYY4JGD3A","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01052","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-02T07:54:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c0196bd91b80f82f8038f1df0294ff333fef1884615cbb71388a8e3e9564bcb4","abstract_canon_sha256":"19a7eadf348ee7122067236a2f80efbdc8d6b2b38c7824d0632f5bc9a1b2ba30"},"schema_version":"1.0"},"canonical_sha256":"fe9b3524a1707f7f51e5bab18e24c3d83ca002de570917f673916bd32e75a783","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:25.682907Z","signature_b64":"f4ncgzPzlIQ375XxBzInJZkcL5d/i1NrxlphzT0Hws2A5Gx7nuPnkaiwZN9chmSCPwVb1AW5gH0sVve/Vd2NBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9b3524a1707f7f51e5bab18e24c3d83ca002de570917f673916bd32e75a783","last_reissued_at":"2026-07-05T07:13:25.682442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:25.682442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01052","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:13:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8h3LKRznGTeXHZkzu8SyaY7TPTHAh3zX8Alhk8ODuqAhh/dkR7ZM5RLKTYhNEGLNf3oM0QnTxXJaLE4V+LtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:47:50.410869Z"},"content_sha256":"874611a402573cb95eae8e1948d01ffb96a0550af9798c79bca69f4810d24877","schema_version":"1.0","event_id":"sha256:874611a402573cb95eae8e1948d01ffb96a0550af9798c79bca69f4810d24877"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:72NTKJFBOB7X6UPFXKYY4JGD3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ga\\\"el Richard, Mathieu Fontaine, Micka\\\"el Chen, Patrick P\\'erez, Slim Essid, Victor Letzelter","submitted_at":"2023-11-02T07:54:03Z","abstract_excerpt":"We introduce Resilient Multiple Choice Learning (rMCL), an extension of the MCL approach for conditional distribution estimation in regression settings where multiple targets may be sampled for each training input. Multiple Choice Learning is a simple framework to tackle multimodal density estimation, using the Winner-Takes-All (WTA) loss for a set of hypotheses. In regression settings, the existing MCL variants focus on merging the hypotheses, thereby eventually sacrificing the diversity of the predictions. In contrast, our method relies on a novel learned scoring scheme underpinned by a math"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01052","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.01052/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:13:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vyFxqYdrHRwCtWJpj3qBAQQh04JhXERaFwZQ8KdrsZ66XhQFU12v3OPOlVx2lVh0Io5D4j4eXgKsbMr7LYbeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:47:50.411268Z"},"content_sha256":"38e94b871c4534a7e74fec237c28806404a858a1baf228ba6ec2b329123008f0","schema_version":"1.0","event_id":"sha256:38e94b871c4534a7e74fec237c28806404a858a1baf228ba6ec2b329123008f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/72NTKJFBOB7X6UPFXKYY4JGD3A/bundle.json","state_url":"https://pith.science/pith/72NTKJFBOB7X6UPFXKYY4JGD3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/72NTKJFBOB7X6UPFXKYY4JGD3A/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T17:47:50Z","links":{"resolver":"https://pith.science/pith/72NTKJFBOB7X6UPFXKYY4JGD3A","bundle":"https://pith.science/pith/72NTKJFBOB7X6UPFXKYY4JGD3A/bundle.json","state":"https://pith.science/pith/72NTKJFBOB7X6UPFXKYY4JGD3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/72NTKJFBOB7X6UPFXKYY4JGD3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:72NTKJFBOB7X6UPFXKYY4JGD3A","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"19a7eadf348ee7122067236a2f80efbdc8d6b2b38c7824d0632f5bc9a1b2ba30","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-02T07:54:03Z","title_canon_sha256":"c0196bd91b80f82f8038f1df0294ff333fef1884615cbb71388a8e3e9564bcb4"},"schema_version":"1.0","source":{"id":"2311.01052","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01052","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01052v2","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01052","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"pith_short_12","alias_value":"72NTKJFBOB7X","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"pith_short_16","alias_value":"72NTKJFBOB7X6UPF","created_at":"2026-07-05T07:13:25Z"},{"alias_kind":"pith_short_8","alias_value":"72NTKJFB","created_at":"2026-07-05T07:13:25Z"}],"graph_snapshots":[{"event_id":"sha256:38e94b871c4534a7e74fec237c28806404a858a1baf228ba6ec2b329123008f0","target":"graph","created_at":"2026-07-05T07:13:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.01052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Resilient Multiple Choice Learning (rMCL), an extension of the MCL approach for conditional distribution estimation in regression settings where multiple targets may be sampled for each training input. Multiple Choice Learning is a simple framework to tackle multimodal density estimation, using the Winner-Takes-All (WTA) loss for a set of hypotheses. In regression settings, the existing MCL variants focus on merging the hypotheses, thereby eventually sacrificing the diversity of the predictions. In contrast, our method relies on a novel learned scoring scheme underpinned by a math","authors_text":"Ga\\\"el Richard, Mathieu Fontaine, Micka\\\"el Chen, Patrick P\\'erez, Slim Essid, Victor Letzelter","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-02T07:54:03Z","title":"Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01052","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:874611a402573cb95eae8e1948d01ffb96a0550af9798c79bca69f4810d24877","target":"record","created_at":"2026-07-05T07:13:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"19a7eadf348ee7122067236a2f80efbdc8d6b2b38c7824d0632f5bc9a1b2ba30","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-11-02T07:54:03Z","title_canon_sha256":"c0196bd91b80f82f8038f1df0294ff333fef1884615cbb71388a8e3e9564bcb4"},"schema_version":"1.0","source":{"id":"2311.01052","kind":"arxiv","version":2}},"canonical_sha256":"fe9b3524a1707f7f51e5bab18e24c3d83ca002de570917f673916bd32e75a783","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe9b3524a1707f7f51e5bab18e24c3d83ca002de570917f673916bd32e75a783","first_computed_at":"2026-07-05T07:13:25.682442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:25.682442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f4ncgzPzlIQ375XxBzInJZkcL5d/i1NrxlphzT0Hws2A5Gx7nuPnkaiwZN9chmSCPwVb1AW5gH0sVve/Vd2NBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:25.682907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01052","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:874611a402573cb95eae8e1948d01ffb96a0550af9798c79bca69f4810d24877","sha256:38e94b871c4534a7e74fec237c28806404a858a1baf228ba6ec2b329123008f0"],"state_sha256":"25ba8c2751d03e469cef267f68cb8f7a90d7cfc58350fd8897b40cb9c184ea40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w0o0P+lEcVgC7Wma4aL67kaOevQd89f8ZeAzv9pl6tiaB+aKa7GzenF+AHWAktY6K/vL+Ooq7imD5KmCmqUDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:47:50.413266Z","bundle_sha256":"e02649c1c862e0505633dc73bf2bef8dbfae07dce791e4760f6dbe1295646ea5"}}